… | |
… | |
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
27 | } |
27 | } |
28 | |
28 | |
29 | =head1 DESCRIPTION |
29 | =head1 DESCRIPTION |
30 | |
30 | |
31 | WARNING! This module is very new, and not very well tested (that's up |
|
|
32 | to you to do). Furthermore, details of the implementation might change |
|
|
33 | freely before version 1.0. And lastly, most extensions depend on an IANA |
|
|
34 | assignment, and until that assignment is official, this implementation is |
|
|
35 | not interoperable with other implementations (even future versions of this |
|
|
36 | module) until the assignment is done. |
|
|
37 | |
|
|
38 | You are still invited to try out CBOR, and this module. |
|
|
39 | |
|
|
40 | This module converts Perl data structures to the Concise Binary Object |
31 | This module converts Perl data structures to the Concise Binary Object |
41 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
32 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
42 | format that aims to use a superset of the JSON data model, i.e. when you |
33 | format that aims to use an (almost) superset of the JSON data model, i.e. |
43 | can represent something in JSON, you should be able to represent it in |
34 | when you can represent something useful in JSON, you should be able to |
44 | CBOR. |
35 | represent it in CBOR. |
45 | |
36 | |
46 | In short, CBOR is a faster and very compact binary alternative to JSON, |
37 | In short, CBOR is a faster and quite compact binary alternative to JSON, |
47 | with the added ability of supporting serialisation of Perl objects. (JSON |
38 | with the added ability of supporting serialisation of Perl objects. (JSON |
48 | often compresses better than CBOR though, so if you plan to compress the |
39 | often compresses better than CBOR though, so if you plan to compress the |
49 | data later you might want to compare both formats first). |
40 | data later and speed is less important you might want to compare both |
|
|
41 | formats first). |
50 | |
42 | |
51 | To give you a general idea about speed, with texts in the megabyte range, |
43 | To give you a general idea about speed, with texts in the megabyte range, |
52 | C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or |
44 | C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or |
53 | L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the |
45 | L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the |
54 | data, the worse L<Storable> performs in comparison. |
46 | data, the worse L<Storable> performs in comparison. |
55 | |
47 | |
56 | As for compactness, C<CBOR::XS> encoded data structures are usually about |
48 | Regarding compactness, C<CBOR::XS>-encoded data structures are usually |
57 | 20% smaller than the same data encoded as (compact) JSON or L<Storable>. |
49 | about 20% smaller than the same data encoded as (compact) JSON or |
|
|
50 | L<Storable>. |
58 | |
51 | |
59 | In addition to the core CBOR data format, this module implements a number |
52 | In addition to the core CBOR data format, this module implements a |
60 | of extensions, to support cyclic and self-referencing data structures |
53 | number of extensions, to support cyclic and shared data structures |
61 | (see C<allow_sharing>), string deduplication (see C<pack_strings>) and |
54 | (see C<allow_sharing> and C<allow_cycles>), string deduplication (see |
62 | scalar references (always enabled). |
55 | C<pack_strings>) and scalar references (always enabled). |
63 | |
56 | |
64 | The primary goal of this module is to be I<correct> and the secondary goal |
57 | The primary goal of this module is to be I<correct> and the secondary goal |
65 | is to be I<fast>. To reach the latter goal it was written in C. |
58 | is to be I<fast>. To reach the latter goal it was written in C. |
66 | |
59 | |
67 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
60 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
… | |
… | |
71 | |
64 | |
72 | package CBOR::XS; |
65 | package CBOR::XS; |
73 | |
66 | |
74 | use common::sense; |
67 | use common::sense; |
75 | |
68 | |
76 | our $VERSION = 0.09; |
69 | our $VERSION = 1.11; |
77 | our @ISA = qw(Exporter); |
70 | our @ISA = qw(Exporter); |
78 | |
71 | |
79 | our @EXPORT = qw(encode_cbor decode_cbor); |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
80 | |
73 | |
81 | use Exporter; |
74 | use Exporter; |
… | |
… | |
187 | reference to the earlier value. |
180 | reference to the earlier value. |
188 | |
181 | |
189 | This means that such values will only be encoded once, and will not result |
182 | This means that such values will only be encoded once, and will not result |
190 | in a deep cloning of the value on decode, in decoders supporting the value |
183 | in a deep cloning of the value on decode, in decoders supporting the value |
191 | sharing extension. This also makes it possible to encode cyclic data |
184 | sharing extension. This also makes it possible to encode cyclic data |
192 | structures. |
185 | structures (which need C<allow_cycles> to ne enabled to be decoded by this |
|
|
186 | module). |
193 | |
187 | |
194 | It is recommended to leave it off unless you know your |
188 | It is recommended to leave it off unless you know your |
195 | communication partner supports the value sharing extensions to CBOR |
189 | communication partner supports the value sharing extensions to CBOR |
196 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
190 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
197 | resulting data structure might be unusable. |
191 | resulting data structure might be unusable. |
198 | |
192 | |
199 | Detecting shared values incurs a runtime overhead when values are encoded |
193 | Detecting shared values incurs a runtime overhead when values are encoded |
200 | that have a reference counter large than one, and might unnecessarily |
194 | that have a reference counter large than one, and might unnecessarily |
201 | increase the encoded size, as potentially shared values are encode as |
195 | increase the encoded size, as potentially shared values are encode as |
202 | sharable whether or not they are actually shared. |
196 | shareable whether or not they are actually shared. |
203 | |
197 | |
204 | At the moment, only targets of references can be shared (e.g. scalars, |
198 | At the moment, only targets of references can be shared (e.g. scalars, |
205 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
199 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
206 | an array with multiple "copies" of the I<same> string, which are hard but |
200 | an array with multiple "copies" of the I<same> string, which are hard but |
207 | not impossible to create in Perl, are not supported (this is the same as |
201 | not impossible to create in Perl, are not supported (this is the same as |
… | |
… | |
212 | structures cannot be encoded in this mode. |
206 | structures cannot be encoded in this mode. |
213 | |
207 | |
214 | This option does not affect C<decode> in any way - shared values and |
208 | This option does not affect C<decode> in any way - shared values and |
215 | references will always be decoded properly if present. |
209 | references will always be decoded properly if present. |
216 | |
210 | |
|
|
211 | =item $cbor = $cbor->allow_cycles ([$enable]) |
|
|
212 | |
|
|
213 | =item $enabled = $cbor->get_allow_cycles |
|
|
214 | |
|
|
215 | If C<$enable> is true (or missing), then C<decode> will happily decode |
|
|
216 | self-referential (cyclic) data structures. By default these will not be |
|
|
217 | decoded, as they need manual cleanup to avoid memory leaks, so code that |
|
|
218 | isn't prepared for this will not leak memory. |
|
|
219 | |
|
|
220 | If C<$enable> is false (the default), then C<decode> will throw an error |
|
|
221 | when it encounters a self-referential/cyclic data structure. |
|
|
222 | |
|
|
223 | This option does not affect C<encode> in any way - shared values and |
|
|
224 | references will always be decoded properly if present. |
|
|
225 | |
217 | =item $cbor = $cbor->pack_strings ([$enable]) |
226 | =item $cbor = $cbor->pack_strings ([$enable]) |
218 | |
227 | |
219 | =item $enabled = $cbor->get_pack_strings |
228 | =item $enabled = $cbor->get_pack_strings |
220 | |
229 | |
221 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
230 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
… | |
… | |
233 | the standard CBOR way. |
242 | the standard CBOR way. |
234 | |
243 | |
235 | This option does not affect C<decode> in any way - string references will |
244 | This option does not affect C<decode> in any way - string references will |
236 | always be decoded properly if present. |
245 | always be decoded properly if present. |
237 | |
246 | |
|
|
247 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
|
|
248 | |
|
|
249 | =item $enabled = $cbor->get_validate_utf8 |
|
|
250 | |
|
|
251 | If C<$enable> is true (or missing), then C<decode> will validate that |
|
|
252 | elements (text strings) containing UTF-8 data in fact contain valid UTF-8 |
|
|
253 | data (instead of blindly accepting it). This validation obviously takes |
|
|
254 | extra time during decoding. |
|
|
255 | |
|
|
256 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
|
|
257 | of the official UTF-8. |
|
|
258 | |
|
|
259 | If C<$enable> is false (the default), then C<decode> will blindly accept |
|
|
260 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
|
|
261 | regardless of whether thats true or not. |
|
|
262 | |
|
|
263 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
|
|
264 | generally not crash or do similarly evil things. Extensions might be not |
|
|
265 | so forgiving, so it's recommended to turn on this setting if you receive |
|
|
266 | untrusted CBOR. |
|
|
267 | |
|
|
268 | This option does not affect C<encode> in any way - strings that are |
|
|
269 | supposedly valid UTF-8 will simply be dumped into the resulting CBOR |
|
|
270 | string without checking whether that is, in fact, true or not. |
|
|
271 | |
238 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
272 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
239 | |
273 | |
240 | =item $cb_or_undef = $cbor->get_filter |
274 | =item $cb_or_undef = $cbor->get_filter |
241 | |
275 | |
242 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
276 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
… | |
… | |
259 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
293 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
260 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
294 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
261 | a code reference that is called with tag and value, and is responsible for |
295 | a code reference that is called with tag and value, and is responsible for |
262 | decoding the value. If no entry exists, it returns no values. |
296 | decoding the value. If no entry exists, it returns no values. |
263 | |
297 | |
264 | Example: decode all tags not handled internally into CBOR::XS::Tagged |
298 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
265 | objects, with no other special handling (useful when working with |
299 | objects, with no other special handling (useful when working with |
266 | potentially "unsafe" CBOR data). |
300 | potentially "unsafe" CBOR data). |
267 | |
301 | |
268 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
302 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
269 | |
303 | |
… | |
… | |
323 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
357 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
324 | support, 64 bit integers will be truncated or otherwise corrupted. |
358 | support, 64 bit integers will be truncated or otherwise corrupted. |
325 | |
359 | |
326 | =item byte strings |
360 | =item byte strings |
327 | |
361 | |
328 | Byte strings will become octet strings in Perl (the byte values 0..255 |
362 | Byte strings will become octet strings in Perl (the Byte values 0..255 |
329 | will simply become characters of the same value in Perl). |
363 | will simply become characters of the same value in Perl). |
330 | |
364 | |
331 | =item UTF-8 strings |
365 | =item UTF-8 strings |
332 | |
366 | |
333 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
367 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
… | |
… | |
356 | =item tagged values |
390 | =item tagged values |
357 | |
391 | |
358 | Tagged items consists of a numeric tag and another CBOR value. |
392 | Tagged items consists of a numeric tag and another CBOR value. |
359 | |
393 | |
360 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
394 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
361 | for details. |
395 | for details on which tags are handled how. |
362 | |
396 | |
363 | =item anything else |
397 | =item anything else |
364 | |
398 | |
365 | Anything else (e.g. unsupported simple values) will raise a decoding |
399 | Anything else (e.g. unsupported simple values) will raise a decoding |
366 | error. |
400 | error. |
… | |
… | |
369 | |
403 | |
370 | |
404 | |
371 | =head2 PERL -> CBOR |
405 | =head2 PERL -> CBOR |
372 | |
406 | |
373 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
407 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
374 | truly typeless language, so we can only guess which CBOR type is meant by |
408 | typeless language. That means this module can only guess which CBOR type |
375 | a Perl value. |
409 | is meant by a perl value. |
376 | |
410 | |
377 | =over 4 |
411 | =over 4 |
378 | |
412 | |
379 | =item hash references |
413 | =item hash references |
380 | |
414 | |
381 | Perl hash references become CBOR maps. As there is no inherent ordering in |
415 | Perl hash references become CBOR maps. As there is no inherent ordering in |
382 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
416 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
383 | order. |
417 | order. This order can be different each time a hahs is encoded. |
384 | |
418 | |
385 | Currently, tied hashes will use the indefinite-length format, while normal |
419 | Currently, tied hashes will use the indefinite-length format, while normal |
386 | hashes will use the fixed-length format. |
420 | hashes will use the fixed-length format. |
387 | |
421 | |
388 | =item array references |
422 | =item array references |
389 | |
423 | |
390 | Perl array references become fixed-length CBOR arrays. |
424 | Perl array references become fixed-length CBOR arrays. |
391 | |
425 | |
392 | =item other references |
426 | =item other references |
393 | |
427 | |
394 | Other unblessed references are generally not allowed and will cause an |
428 | Other unblessed references will be represented using |
395 | exception to be thrown, except for references to the integers C<0> and |
429 | the indirection tag extension (tag value C<22098>, |
396 | C<1>, which get turned into false and true in CBOR. |
430 | L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed |
|
|
431 | to be able to decode these values somehow, by either "doing the right |
|
|
432 | thing", decoding into a generic tagged object, simply ignoring the tag, or |
|
|
433 | something else. |
397 | |
434 | |
398 | =item CBOR::XS::Tagged objects |
435 | =item CBOR::XS::Tagged objects |
399 | |
436 | |
400 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
437 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
401 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
438 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
402 | be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to |
439 | be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to |
403 | create such objects. |
440 | create such objects. |
404 | |
441 | |
405 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
442 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
406 | |
443 | |
407 | These special values become CBOR true, CBOR false and CBOR undefined |
444 | These special values become CBOR true, CBOR false and CBOR undefined |
… | |
… | |
424 | # dump as number |
461 | # dump as number |
425 | encode_cbor [2] # yields [2] |
462 | encode_cbor [2] # yields [2] |
426 | encode_cbor [-3.0e17] # yields [-3e+17] |
463 | encode_cbor [-3.0e17] # yields [-3e+17] |
427 | my $value = 5; encode_cbor [$value] # yields [5] |
464 | my $value = 5; encode_cbor [$value] # yields [5] |
428 | |
465 | |
429 | # used as string, so dump as string |
466 | # used as string, so dump as string (either byte or text) |
430 | print $value; |
467 | print $value; |
431 | encode_cbor [$value] # yields ["5"] |
468 | encode_cbor [$value] # yields ["5"] |
432 | |
469 | |
433 | # undef becomes null |
470 | # undef becomes null |
434 | encode_cbor [undef] # yields [null] |
471 | encode_cbor [undef] # yields [null] |
… | |
… | |
437 | |
474 | |
438 | my $x = 3.1; # some variable containing a number |
475 | my $x = 3.1; # some variable containing a number |
439 | "$x"; # stringified |
476 | "$x"; # stringified |
440 | $x .= ""; # another, more awkward way to stringify |
477 | $x .= ""; # another, more awkward way to stringify |
441 | print $x; # perl does it for you, too, quite often |
478 | print $x; # perl does it for you, too, quite often |
|
|
479 | |
|
|
480 | You can force whether a string ie encoded as byte or text string by using |
|
|
481 | C<utf8::upgrade> and C<utf8::downgrade>): |
|
|
482 | |
|
|
483 | utf8::upgrade $x; # encode $x as text string |
|
|
484 | utf8::downgrade $x; # encode $x as byte string |
|
|
485 | |
|
|
486 | Perl doesn't define what operations up- and downgrade strings, so if the |
|
|
487 | difference between byte and text is important, you should up- or downgrade |
|
|
488 | your string as late as possible before encoding. |
442 | |
489 | |
443 | You can force the type to be a CBOR number by numifying it: |
490 | You can force the type to be a CBOR number by numifying it: |
444 | |
491 | |
445 | my $x = "3"; # some variable containing a string |
492 | my $x = "3"; # some variable containing a string |
446 | $x += 0; # numify it, ensuring it will be dumped as a number |
493 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
459 | |
506 | |
460 | =back |
507 | =back |
461 | |
508 | |
462 | =head2 OBJECT SERIALISATION |
509 | =head2 OBJECT SERIALISATION |
463 | |
510 | |
|
|
511 | This module implements both a CBOR-specific and the generic |
|
|
512 | L<Types::Serialier> object serialisation protocol. The following |
|
|
513 | subsections explain both methods. |
|
|
514 | |
|
|
515 | =head3 ENCODING |
|
|
516 | |
464 | This module knows two way to serialise a Perl object: The CBOR-specific |
517 | This module knows two way to serialise a Perl object: The CBOR-specific |
465 | way, and the generic way. |
518 | way, and the generic way. |
466 | |
519 | |
467 | Whenever the encoder encounters a Perl object that it cnanot serialise |
520 | Whenever the encoder encounters a Perl object that it cannot serialise |
468 | directly (most of them), it will first look up the C<TO_CBOR> method on |
521 | directly (most of them), it will first look up the C<TO_CBOR> method on |
469 | it. |
522 | it. |
470 | |
523 | |
471 | If it has a C<TO_CBOR> method, it will call it with the object as only |
524 | If it has a C<TO_CBOR> method, it will call it with the object as only |
472 | argument, and expects exactly one return value, which it will then |
525 | argument, and expects exactly one return value, which it will then |
… | |
… | |
478 | |
531 | |
479 | The C<FREEZE> method can return any number of values (i.e. zero or |
532 | The C<FREEZE> method can return any number of values (i.e. zero or |
480 | more). These will be encoded as CBOR perl object, together with the |
533 | more). These will be encoded as CBOR perl object, together with the |
481 | classname. |
534 | classname. |
482 | |
535 | |
|
|
536 | These methods I<MUST NOT> change the data structure that is being |
|
|
537 | serialised. Failure to comply to this can result in memory corruption - |
|
|
538 | and worse. |
|
|
539 | |
483 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
540 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
484 | with an error. |
541 | with an error. |
485 | |
542 | |
|
|
543 | =head3 DECODING |
|
|
544 | |
486 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
545 | Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded, |
487 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
546 | but objects encoded via C<FREEZE> can be decoded using the following |
|
|
547 | protocol: |
488 | |
548 | |
489 | When an encoded CBOR perl object is encountered by the decoder, it will |
549 | When an encoded CBOR perl object is encountered by the decoder, it will |
490 | look up the C<THAW> method, by using the stored classname, and will fail |
550 | look up the C<THAW> method, by using the stored classname, and will fail |
491 | if the method cannot be found. |
551 | if the method cannot be found. |
492 | |
552 | |
493 | After the lookup it will call the C<THAW> method with the stored classname |
553 | After the lookup it will call the C<THAW> method with the stored classname |
494 | as first argument, the constant string C<CBOR> as second argument, and all |
554 | as first argument, the constant string C<CBOR> as second argument, and all |
495 | values returned by C<FREEZE> as remaining arguments. |
555 | values returned by C<FREEZE> as remaining arguments. |
496 | |
556 | |
497 | =head4 EXAMPLES |
557 | =head3 EXAMPLES |
498 | |
558 | |
499 | Here is an example C<TO_CBOR> method: |
559 | Here is an example C<TO_CBOR> method: |
500 | |
560 | |
501 | sub My::Object::TO_CBOR { |
561 | sub My::Object::TO_CBOR { |
502 | my ($obj) = @_; |
562 | my ($obj) = @_; |
… | |
… | |
513 | |
573 | |
514 | sub URI::TO_CBOR { |
574 | sub URI::TO_CBOR { |
515 | my ($self) = @_; |
575 | my ($self) = @_; |
516 | my $uri = "$self"; # stringify uri |
576 | my $uri = "$self"; # stringify uri |
517 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
577 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
518 | CBOR::XS::tagged 32, "$_[0]" |
578 | CBOR::XS::tag 32, "$_[0]" |
519 | } |
579 | } |
520 | |
580 | |
521 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
581 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
522 | URI. |
582 | URI. |
523 | |
583 | |
… | |
… | |
685 | |
745 | |
686 | These tags are automatically created (and decoded) for serialisable |
746 | These tags are automatically created (and decoded) for serialisable |
687 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
747 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
688 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
748 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
689 | |
749 | |
690 | =item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
750 | =item 28, 29 (shareable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
691 | |
751 | |
692 | These tags are automatically decoded when encountered, resulting in |
752 | These tags are automatically decoded when encountered (and they do not |
|
|
753 | result in a cyclic data structure, see C<allow_cycles>), resulting in |
693 | shared values in the decoded object. They are only encoded, however, when |
754 | shared values in the decoded object. They are only encoded, however, when |
694 | C<allow_sharable> is enabled. |
755 | C<allow_sharing> is enabled. |
|
|
756 | |
|
|
757 | Not all shared values can be successfully decoded: values that reference |
|
|
758 | themselves will I<currently> decode as C<undef> (this is not the same |
|
|
759 | as a reference pointing to itself, which will be represented as a value |
|
|
760 | that contains an indirect reference to itself - these will be decoded |
|
|
761 | properly). |
|
|
762 | |
|
|
763 | Note that considerably more shared value data structures can be decoded |
|
|
764 | than will be encoded - currently, only values pointed to by references |
|
|
765 | will be shared, others will not. While non-reference shared values can be |
|
|
766 | generated in Perl with some effort, they were considered too unimportant |
|
|
767 | to be supported in the encoder. The decoder, however, will decode these |
|
|
768 | values as shared values. |
695 | |
769 | |
696 | =item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
770 | =item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
697 | |
771 | |
698 | These tags are automatically decoded when encountered. They are only |
772 | These tags are automatically decoded when encountered. They are only |
699 | encoded, however, when C<pack_strings> is enabled. |
773 | encoded, however, when C<pack_strings> is enabled. |
… | |
… | |
724 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
798 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
725 | provide these modules. The decoding usually fails with an exception if the |
799 | provide these modules. The decoding usually fails with an exception if the |
726 | required module cannot be loaded. |
800 | required module cannot be loaded. |
727 | |
801 | |
728 | =over 4 |
802 | =over 4 |
|
|
803 | |
|
|
804 | =item 0, 1 (date/time string, seconds since the epoch) |
|
|
805 | |
|
|
806 | These tags are decoded into L<Time::Piece> objects. The corresponding |
|
|
807 | C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently. |
|
|
808 | |
|
|
809 | The L<Time::Piece> API is generally surprisingly bad, and fractional |
|
|
810 | seconds are only accidentally kept intact, so watch out. On the plus side, |
|
|
811 | the module comes with perl since 5.10, which has to count for something. |
729 | |
812 | |
730 | =item 2, 3 (positive/negative bignum) |
813 | =item 2, 3 (positive/negative bignum) |
731 | |
814 | |
732 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
815 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
733 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
816 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
… | |
… | |
867 | properly. Half precision types are accepted, but not encoded. |
950 | properly. Half precision types are accepted, but not encoded. |
868 | |
951 | |
869 | Strict mode and canonical mode are not implemented. |
952 | Strict mode and canonical mode are not implemented. |
870 | |
953 | |
871 | |
954 | |
|
|
955 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
|
|
956 | |
|
|
957 | On perls that were built without 64 bit integer support (these are rare |
|
|
958 | nowadays, even on 32 bit architectures), support for any kind of 64 bit |
|
|
959 | integer in CBOR is very limited - most likely, these 64 bit values will |
|
|
960 | be truncated, corrupted, or otherwise not decoded correctly. This also |
|
|
961 | includes string, array and map sizes that are stored as 64 bit integers. |
|
|
962 | |
|
|
963 | |
872 | =head1 THREADS |
964 | =head1 THREADS |
873 | |
965 | |
874 | This module is I<not> guaranteed to be thread safe and there are no |
966 | This module is I<not> guaranteed to be thread safe and there are no |
875 | plans to change this until Perl gets thread support (as opposed to the |
967 | plans to change this until Perl gets thread support (as opposed to the |
876 | horribly slow so-called "threads" which are simply slow and bloated |
968 | horribly slow so-called "threads" which are simply slow and bloated |
… | |
… | |
889 | service. I put the contact address into my modules for a reason. |
981 | service. I put the contact address into my modules for a reason. |
890 | |
982 | |
891 | =cut |
983 | =cut |
892 | |
984 | |
893 | our %FILTER = ( |
985 | our %FILTER = ( |
894 | # 0 # rfc4287 datetime, utf-8 |
986 | 0 => sub { # rfc4287 datetime, utf-8 |
895 | # 1 # unix timestamp, any |
987 | require Time::Piece; |
|
|
988 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
|
|
989 | # from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything |
|
|
990 | # else either. Whats incredibe over standard strptime totally escapes me. |
|
|
991 | # doesn't do fractional times, either. sigh. |
|
|
992 | # In fact, it's all a lie, it uses whatever strptime it wants, and of course, |
|
|
993 | # they are all incomptible. The openbsd one simply ignores %z (but according to the |
|
|
994 | # docs, it would be much more incredibly flexible). |
|
|
995 | scalar eval { |
|
|
996 | my $s = $_[1]; |
|
|
997 | |
|
|
998 | $s =~ s/Z$/+00:00/; |
|
|
999 | $s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$// |
|
|
1000 | or die; |
|
|
1001 | |
|
|
1002 | my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully |
|
|
1003 | my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S"); |
|
|
1004 | |
|
|
1005 | Time::Piece::gmtime ($d->epoch + $b) |
|
|
1006 | } || die "corrupted CBOR date/time string ($_[0])"; |
|
|
1007 | }, |
|
|
1008 | |
|
|
1009 | 1 => sub { # seconds since the epoch, possibly fractional |
|
|
1010 | require Time::Piece; |
|
|
1011 | scalar Time::Piece::gmtime (pop) |
|
|
1012 | }, |
896 | |
1013 | |
897 | 2 => sub { # pos bigint |
1014 | 2 => sub { # pos bigint |
898 | require Math::BigInt; |
1015 | require Math::BigInt; |
899 | Math::BigInt->new ("0x" . unpack "H*", pop) |
1016 | Math::BigInt->new ("0x" . unpack "H*", pop) |
900 | }, |
1017 | }, |
… | |
… | |
936 | } |
1053 | } |
937 | |
1054 | |
938 | sub URI::TO_CBOR { |
1055 | sub URI::TO_CBOR { |
939 | my $uri = $_[0]->as_string; |
1056 | my $uri = $_[0]->as_string; |
940 | utf8::upgrade $uri; |
1057 | utf8::upgrade $uri; |
941 | CBOR::XS::tag 32, $uri |
1058 | tag 32, $uri |
942 | } |
1059 | } |
943 | |
1060 | |
944 | sub Math::BigInt::TO_CBOR { |
1061 | sub Math::BigInt::TO_CBOR { |
945 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
1062 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
946 | $_[0]->numify |
1063 | $_[0]->numify |
947 | } else { |
1064 | } else { |
948 | my $hex = substr $_[0]->as_hex, 2; |
1065 | my $hex = substr $_[0]->as_hex, 2; |
949 | $hex = "0$hex" if 1 & length $hex; # sigh |
1066 | $hex = "0$hex" if 1 & length $hex; # sigh |
950 | CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
1067 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
951 | } |
1068 | } |
952 | } |
1069 | } |
953 | |
1070 | |
954 | sub Math::BigFloat::TO_CBOR { |
1071 | sub Math::BigFloat::TO_CBOR { |
955 | my ($m, $e) = $_[0]->parts; |
1072 | my ($m, $e) = $_[0]->parts; |
956 | CBOR::XS::tag 4, [$e->numify, $m] |
1073 | tag 4, [$e->numify, $m] |
|
|
1074 | } |
|
|
1075 | |
|
|
1076 | sub Time::Piece::TO_CBOR { |
|
|
1077 | tag 1, $_[0]->epoch |
957 | } |
1078 | } |
958 | |
1079 | |
959 | XSLoader::load "CBOR::XS", $VERSION; |
1080 | XSLoader::load "CBOR::XS", $VERSION; |
960 | |
1081 | |
961 | =head1 SEE ALSO |
1082 | =head1 SEE ALSO |